Towards low-complexity wireless technology classification across multiple environments

Abstract To cope with the increasing number of co-existing wireless standards, complex machine learning techniques have been proposed for wireless technology classification. However, machine learning techniques in the scientific literature suffer from some shortcomings, namely: (i) they are often trained using data from only a single measurement location, and as such the results do not necessarily generalise and (ii) they typically do not evaluate complexity/accuracy trade-offs of the proposed solutions. To remedy these shortcomings, this paper investigates which resource-friendly approaches are suitable across multiple heterogeneous environments. To this end, the paper designs and evaluates classifiers for LTE, Wi-Fi and DVB-T technologies using multiple datasets to investigate the complexity/accuracy trade-offs between manual feature extraction and automatic feature learning techniques. Our wireless technology classification reaches an accuracy up to 99%. Moreover, we propose the use of data augmentation techniques to extend these results to unseen environments at the cost of only 2% reduction in accuracy. When concerning generalisation capabilities, complex automatic learning techniques surpass simple manual feature extraction approaches. Finally, the complexity of these automatic learning techniques can be significantly reduced by using computationally less intensive received signal strength indicator data while reaching acceptable accuracies in unseen environments (92% vs 97%).